Unverified60% confidenceFactExact time
DeepSeek-V4-Flash-Vision-Exp adopts a MoE architecture with approximately 305B total parameters, activating only approximately 13B per token, for an activation rate of approximately 4.6%.
2
Sources
60%
Confidence
Long-term
Relevance
9/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDeepSeek V4 Flash is a cloud-based model focused on high throughput, with an inference speed of approximately 140 tokens per second.74% similarUnverifiedDeepSeek released the weights for the first vision version of V4, with a model scale of 305B (approximately 305 billion parameters).73% similarUnverifiedDeepSeek-V4.1-Flash-1017 supports a 1 million token context, with a recommended maximum output of 256K or more.72% similarUnverifiedDeepSeek-V4.1-Flash has 763B parameters, BF16 weights are about 1.5 TB, the official FP4/FP8 checkpoint is 475.2 GiB, and coolbho3k's 3-bit EXL3 package compresses it to 309.3 GiB.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/849869API
curl https://kongchang.com/api/v1/knowledge/claims/849869MCP
get_claim(id=849869)